ByteDance launches Bernini, a unified video generation and editing model built on Wan‑2.2
Bernini merges an MLLM‑based semantic planner with a DiT renderer, enabling both text‑driven video generation and editing within a single model. It leverages ByteDance's Wan‑2.2 architecture and supports reference images or videos for content insertion and style guidance. The work is detailed in a new arXiv preprint.